Hackathon

4. A condition where a trained model over-conforms to training data and does not perform well on new, unseen data.
8. An input that a user feeds to an AI system in order to get a desired result or output.
9. Reducing a matrix (or matrices) created by an earlier convolutional layer to a smaller matrix
11. A real-time object detection algorithm that uses a single forward pass in a neural network to detect and localize objects in images.
12. An AI-generated piece of media depicting a real person or their voice.
13. In AI, a phenomenon wherein a model generates inaccurate or nonsensical output that is not supported by the data it was trained on.
14. The process of making predictions by applying a trained model to unlabeled examples.

1. A basic unit of text that a Large Language Model (LLM) that the model is training and making predictions on. It may be an entire word or parts of a word.
2. Any endpoint in a decision tree.
3. An algorithm for supervised learning of artificial neural networks using gradient descent.
5. A conditional logic where variables can exhibit any degree of truthfulness, ranging from 0 to 1.
6. Restrictions and rules placed on AI systems to make sure that they handle data appropriately and don't generate unethical content.
7. In ML, a state in which a model’s performance is unlikely to improve with further training.
10. A model used as a reference point for comparing how well another model is performing.